{"id":"W1978954330","doi":"10.1198/0003130043277","title":"Bootstrap Methods for Developing Predictive Models","year":2004,"lang":"en","type":"article","venue":"The American Statistician","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":620,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"","keywords":"Resampling; Feature selection; Model selection; Computer science; Statistics; Predictive modelling; Selection (genetic algorithm); Bootstrap aggregating; Variables; Machine learning; Econometrics; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01800799,0.002923939,0.002669169,0.00606935,0.001250535,0.002491271,0.0034441,0.00192555,0.008046326],"category_scores_gemma":[0.07900786,0.001672618,0.002325072,0.004842778,0.001445201,0.002860296,0.003042463,0.004703667,0.005094206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008665287,"about_ca_system_score_gemma":0.002624747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003068457,"about_ca_topic_score_gemma":0.002833245,"domain_scores_codex":[0.988943,0.007630731,0.0006155677,0.0007713976,0.001849386,0.0001900633],"domain_scores_gemma":[0.9650561,0.02861577,0.001237721,0.002352254,0.002459483,0.0002786488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001594906,0.0001825692,0.003438971,0.001015263,0.0009757914,0.0003838032,0.0004468351,0.33391,0.001381683,0.2129845,0.0211094,0.4240117],"study_design_scores_gemma":[0.00008200188,0.00005427375,0.0004450436,0.0001877049,0.00008895907,0.00009624881,0.00006448936,0.7726114,0.0008039493,0.2111779,0.01434145,0.00004651475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005412354,0.0002837115,0.9972101,0.0001230643,0.00005401958,0.0001115838,0.0001660971,0.0008605198,0.0006497901],"genre_scores_gemma":[0.03452104,0.001152204,0.9594849,0.0001597313,0.0002809367,0.001693847,0.001120989,0.0005749039,0.001011343],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01800799,"threshold_uncertainty_score":0.09523654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03567676071956769,"score_gpt":0.3619012094975819,"score_spread":0.3262244487780143,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}